Knowledge Commons of Institute of Automation,CAS
Fast Deep Matting for Portrait Animation on Mobile Phone | |
Bingke Zhu1,2; Yingying Chen1,2; Jinqiao Wang1,2; Si Liu3; Bo Zhang4; Ming Tang1,2 | |
2017 | |
会议名称 | ACM on Multimedia Conference |
会议录名称 | 无 |
卷号 | 无 |
期号 | 无 |
页码 | 297-305 |
会议日期 | October 23 - 27, 2017 |
会议地点 | Mountain View, California, USA |
会议举办国 | 美国 |
会议录编者/会议主办者 | Qiong Liu,Rainer Lienhart,Haohong Wang,Sheng-Wei,Kuan-Ta Chen,Susanne Boll,Yi Ping Phoebe Chen,Gerald Friedland,Jia Li,Shuicheng Yan |
出版地 | Mountain View, California, USA |
出版者 | Qiong Liu,Rainer Lienhart,Haohong Wang,Sheng-Wei,Kuan-Ta Chen,Susanne Boll,Yi Ping Phoebe Chen,Gerald Friedland,Jia Li,Shuicheng Yan |
摘要 | Image matting plays an important role in image and video editing. However, the formulation of image matting is inherently ill-posed. Traditional methods usually employ interaction to deal with the image matting problem with trimaps and strokes, and cannot run on the mobile phone in real-time. In this paper, we propose a real-time automatic deep matting approach for mobile devices. By leveraging the densely connected blocks and the dilated convolution, a light full convolutional network is designed to predict a coarse binary mask for portrait images. And a feathering block, which is edge-preserving and matting adaptive, is further developed to learn the guided filter and transform the binary mask into alpha matte. Finally, an automatic portrait animation system based on fast deep matting is built on mobile devices, which does not need any interaction and can realize real-time matting with 15 fps. The experiments show that the proposed approach achieves comparable results with the state-of-the-art matting solvers. |
关键词 | Portrait Matting Real-time Automatic Mobile Phone |
学科领域 | 计算机科学技术 |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1145/3123266.3123286 |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
WOS研究方向 | 无 |
WOS类目 | 无 |
WOS记录号 | WOS:无 |
EI入藏号 | 无 |
EI主题词 | 无 |
EI分类号 | 无 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/20261 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 3.中国科学院信息工程研究所 4.北京工业大学 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Bingke Zhu,Yingying Chen,Jinqiao Wang,et al. Fast Deep Matting for Portrait Animation on Mobile Phone[C]//Qiong Liu,Rainer Lienhart,Haohong Wang,Sheng-Wei,Kuan-Ta Chen,Susanne Boll,Yi Ping Phoebe Chen,Gerald Friedland,Jia Li,Shuicheng Yan. Mountain View, California, USA:Qiong Liu,Rainer Lienhart,Haohong Wang,Sheng-Wei,Kuan-Ta Chen,Susanne Boll,Yi Ping Phoebe Chen,Gerald Friedland,Jia Li,Shuicheng Yan,2017:297-305. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Fast Deep Matting fo(1949KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论